Directus MCP Server (staminna/mcp-server-claude) is an MCP server listed on the M8ven Trust Index. It scores 56 out of 100, grade D. It declares 41 tools. No publisher has claimed this listing.
Enables comprehensive interaction with Directus CMS including collection management, file operations, flow automation, user management, and schema analysis through natural language commands.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
staminna
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
list_collectionsList all collections in the Directus instance
get_collection_schemaGet the schema for a specific collection
get_collection_itemsGet items from a collection with optional filtering and pagination
create_collectionCreate a new collection with optional fields
delete_collectionDelete a collection (requires confirmation)
create_itemCreate a new item in a collection
update_itemUpdate an existing item in a collection
delete_itemsDelete items from a collection with optional cascade
create_fieldCreate a new field in a collection
update_fieldUpdate an existing field in a collection
delete_fieldDelete a field from a collection (requires confirmation)
bulk_operationsExecute bulk create, update, and delete operations
analyze_collection_schemaAnalyze collection schema with relationship mapping and validation
analyze_relationshipsAnalyze relationships across collections
create_relationshipCreate relationships between collections (O2O, O2M, M2O, M2M, M2A)
validate_collection_schemaValidate collection schema and relationships
diagnose_collection_accessDiagnose collection access issues and permissions
refresh_collection_cacheRefresh Directus collection cache and verify access
validate_collection_creationValidate that a newly created collection is properly accessible
get_usersGet all users with optional filtering and pagination
get_userGet a specific user by ID
get_filesGet files with optional filtering and pagination
get_flowsGet flows with optional filtering and pagination
get_flowGet a specific flow by ID with optional operations
create_flowCreate a new automation flow
update_flowUpdate an existing flow
delete_flowDelete a flow and all its operations (requires confirmation)
trigger_flowManually trigger a flow execution
get_operationsGet flow operations with optional filtering by flow
get_productsGet products from the products collection with filtering and pagination
create_productCreate a new product in the products collection
update_productUpdate an existing product
get_ordersGet orders from the orders collection
create_orderCreate a new order with order items
get_customersGet customers from the customers collection
create_customerCreate a new customer
get_brandsGet brands from the brands collection
get_categoriesGet categories from the categories collection
get_product_imagesGet product images from the product_images collection
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
axios Vulnerable to Full Man-in-the-Middle via Prototype Pollution Gadget in `config.proxy`
axios Vulnerable to Credential Theft and Response Hijacking via Prototype Pollution Gadget in Config Merge
DIRECTUS_RETRIESDIRECTUS_TIMEOUTDIRECTUS_TOKENYes Static API token with appropriate permissionsDIRECTUS_URLYes Your Directus instance URL (e.g., http://localhost:8065)DIRECTUS_WEBSOCKETLOG_LEVELTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
41/41 tools missing one or more hints — list_collections (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_collection_schema (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_collection_items (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +38 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool test coverage
31/41 tools referenced in tests (76%)
Write tests that reference each tool by name so every tool has at least one test.
Production dependencies are patched
0 critical, 15 high severity in production deps — @modelcontextprotocol/sdk@1.17.4 (high), @modelcontextprotocol/sdk@1.17.4 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/staminna/mcp-server-claude)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check